Model Council

Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...

Security Scan

The skill does what it says: it forwards a question to multiple LLMs through OpenRouter and uses a judge model to pick/synthesize an answer; its requested access and code are consistent with that purpose.

Purpose & Capability

Name/description ask for multi-model consensus via OpenRouter and the package only requires OPENROUTER_API_KEY and contains a script that calls OpenRouter endpoints for chat completions and (optionally) generation-cost info. The default model list and judge selection align with the stated purpose.

Instruction Scope

SKILL.md tells the agent to run the included Python script with the question and optional flags. The script only reads the OPENROUTER_API_KEY environment variable and does network calls to openrouter.ai; it does not read other files, credentials, or unexpected system paths.

Install Mechanism

No install spec is provided (instruction-only + included script). The script uses only Python stdlib (urllib, threading), so nothing is downloaded or written during install. This is a low-risk install model.

Credentials

Only OPENROUTER_API_KEY is required and declared as primaryEnv. The key is necessary and sufficient for forwarding requests to OpenRouter. No other secrets or unrelated env vars are requested or accessed by the code.

Persistence & Privilege

The skill does not request or require always:true and does not attempt to modify other skills or system-wide settings. It runs on-demand and only uses the API key at runtime.

Assessment

This skill is coherent with its stated purpose, but remember it will send whatever you type to external LLMs via OpenRouter and incur API costs. Do not submit sensitive secrets or private data to the council. Verify your OpenRouter account limits and billing, and consider testing with a throwaway question first. If you are uncertain about the publisher, review the included script yourself (it is short and uses only the OpenRouter endpoints) and rotate the API key if you decide to stop using the skill. Finally, monitor usage after enabling the skill to detect unexpected calls or charges.

Get consensus from multiple AI models on any question.

Send your query to 3+ different LLMs simultaneously via OpenRouter. A judge model evaluates all responses and produces a winner, reasoning, and synthesized best answer.

When to Use

• Important decisions — Don't trust one model's opinion
• Code review — Get multiple perspectives on architecture choices
• Research verification — Cross-check facts across models
• Creative work — Compare writing styles and pick the best
• Debugging — When one model is stuck, others might see the issue

How It Works

Your Question
    ├──→ Claude Sonnet 4    ──→ Response A
    ├──→ GPT-4o             ──→ Response B
    └──→ Gemini 2.0 Flash   ──→ Response C
                                    │
                              Judge (Opus) evaluates all
                                    │
                              ├── Winner + Reasoning
                              ├── Synthesized Best Answer
                              └── Cost Breakdown

Quick Start

# Basic usage
python3 {baseDir}/scripts/model_council.py "What's the best database for a real-time analytics dashboard?"

# Custom models
python3 {baseDir}/scripts/model_council.py --models "anthropic/claude-sonnet-4,openai/gpt-4o,google/gemini-2.5-pro" "Your question"

# Custom judge
python3 {baseDir}/scripts/model_council.py --judge "openai/gpt-4o" "Your question"

# JSON output
python3 {baseDir}/scripts/model_council.py --json "Your question"

# Set max tokens per response
python3 {baseDir}/scripts/model_council.py --max-tokens 2000 "Your question"

Configuration

Flag	Default	Description
--models	claude-sonnet-4, gpt-4o, gemini-2.0-flash	Comma-separated model list
--judge	anthropic/claude-opus-4-6	Judge model
--max-tokens	1024	Max tokens per council member
--json	false	Output as JSON
--timeout	60	Timeout per model (seconds)

Environment

Requires OPENROUTER_API_KEY environment variable.

Output Example

═══ MODEL COUNCIL RESULTS ═══

Question: What's the best way to handle auth in a microservices architecture?

── Council Member Responses ──

🤖 anthropic/claude-sonnet-4 ($0.0043)
Use a centralized auth service with JWT tokens...

🤖 openai/gpt-4o ($0.0038)
Implement OAuth 2.0 with an API gateway...

🤖 google/gemini-2.0-flash-001 ($0.0012)
Consider using service mesh with mTLS...

── Judge Verdict (anthropic/claude-opus-4-6, $0.0125) ──

🏆 Winner: anthropic/claude-sonnet-4
Reasoning: Most comprehensive and practical approach...

📝 Synthesized Answer:
The best approach combines elements from all three...

💰 Total Cost: $0.0218

Credits

Built by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.

📅 Need help setting up OpenClaw for your business? Book a free consultation